Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Statistical significance (p < 0.05)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probs
    -0.06
     heute
    -0.06
     già
    -0.06
    _detect
    -0.06
     happened
    -0.05
     Ně
    -0.05
    .Iter
    -0.05
    Men
    -0.05
     decimals
    -0.05
     Pilot
    -0.05
    POSITIVE LOGITS
    ']."</
    0.08
    )').
    0.08
    iker
    0.07
    ocratic
    0.07
    یکی
    0.07
    ozilla
    0.06
     Internet
    0.06
    "=>
    0.06
    CCC
    0.06
    лін
    0.06
    Act Density 0.009%

    No Known Activations